Presentation 2016-10-21
Image Categorization Using Collaborative Mean Attraction
Hiroki Ogihara, Masayuki Mukunoki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we apply Collaborative Mean Attraction (CMA) method, which has been applied to person re-identification problem, to image categorazation problem. Experimental results using the caltech101 dataset reveal that CMA shows better categorization accuracy than standard SVM method, particularly in the case when the training data is relatively small.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Generic Object Recognition / CMA method / ImageNet / Caltech Dataset
Paper # PRMU2016-109
Date of Issue 2016-10-13 (PRMU)

Conference Information
Committee PRMU
Conference Date 2016/10/20(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Eisaku Maeda(NTT)
Vice Chair Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.)
Secretary Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT)
Assistant Masaki Oonishi(AIST) / Takuya Funatomi(NAIST)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Categorization Using Collaborative Mean Attraction
Sub Title (in English)
Keyword(1) Generic Object Recognition
Keyword(2) CMA method
Keyword(3) ImageNet
Keyword(4) Caltech Dataset
Keyword(5)
1st Author's Name Hiroki Ogihara
1st Author's Affiliation University of Miyazaki(Univ. of Miyazaki)
2nd Author's Name Masayuki Mukunoki
2nd Author's Affiliation University of Miyazaki(Univ. of Miyazaki)
Date 2016-10-21
Paper # PRMU2016-109
Volume (vol) vol.116
Number (no) PRMU-259
Page pp.pp.103-106(PRMU),
#Pages 4
Date of Issue 2016-10-13 (PRMU)